Sufficient conditions for convergence of Loopy Belief Propagation
classification
💻 cs.AI
keywords
conditionsbeliefconvergenceknownloopypropagationsufficientalgorithm
read the original abstract
We derive novel sufficient conditions for convergence of Loopy Belief Propagation (also known as the Sum-Product algorithm) to a unique fixed point. Our results improve upon previously known conditions. For binary variables with (anti-)ferromagnetic interactions, our conditions seem to be sharp.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Towards Scalable Quaternary Message-Passing Decoding for Quantum Error Correction
Dilution method for quaternary Min-Sum decoder yields 16% apparent depolarizing threshold up to d=20, outperforms MWPM in finite regimes, and for X-noise beats BP-OSD at d=65 with O(N log² d) complexity.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.